# Automated Cognate Detection as a Supervised Link Prediction Task with Cognate Transformer

arXiv: https://arxiv.org/abs/2402.02926 · HTML: https://mlsanity.com/paper/2402.02926/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- Builds on 4 of its 30 references that are in the map.
- First posted on arXiv 5 Feb 2024.

## Builds on (most cited first, 4 of 4)

- [Are Automatic Methods for Cognate Detection Good Enough for Phylogenetic Reconstruction in Historical Linguistics?](https://mlsanity.com/paper/1804.05416/) (2018)
- [Harnessing Cross-lingual Features to Improve Cognate Detection for Low-resource Languages](https://mlsanity.com/paper/2112.08789/) (2021)
- [Cognate Transformer for Automated Phonological Reconstruction and Cognate Reflex Prediction](https://mlsanity.com/paper/2310.07487/) (2023)
- [Cognition-aware Cognate Detection](https://mlsanity.com/paper/2112.08087/) (2021)

## Built on by (most cited first, 6 of 6)

- [Thank You, Stingray: Multilingual Large Language Models Can Not (Yet) Disambiguate Cross-Lingual Word Sense](https://mlsanity.com/paper/2410.21573/) (2024)
- [A Likelihood Ratio Test of Genetic Relationship among Languages](https://mlsanity.com/paper/2404.00284/) (2024)
- [Unsupervised Protoform Reconstruction through Parsimonious Rule-guided Heuristics and Evolutionary Search](https://mlsanity.com/paper/2506.10614/) (2025)
- [The Cognate Data Bottleneck in Language Phylogenetics](https://mlsanity.com/paper/2507.00911/) (2025)
- [Subword-Based Comparative Linguistics across 242 Languages Using Wikipedia Glottosets](https://mlsanity.com/paper/2601.18791/) (2026)
- [When Similar Means Different: Evaluating LLMs on Arabic--Hebrew Cognates](https://mlsanity.com/paper/2606.13218/) (2026)

## Abstract (arXiv)

Identification of cognates across related languages is one of the primary problems in historical linguistics. Automated cognate identification is helpful for several downstream tasks including identifying sound correspondences, proto-language reconstruction, phylogenetic classification, etc. Previous state-of-the-art methods for cognate identification are mostly based on distributions of phonemes computed across multilingual wordlists and make little use of the cognacy labels that define links among cognate clusters. In this paper, we present a transformer-based architecture inspired by computational biology for the task of automated cognate detection. Beyond a certain amount of supervision, this method performs better than the existing methods, and shows steady improvement with further increase in supervision, thereby proving the efficacy of utilizing the labeled information. We also demonstrate that accepting multiple sequence alignments as input and having an end-to-end architecture with link prediction head saves much computation time while simultaneously yielding superior performance.